# Loss Max-Pooling for Semantic Image Segmentation

arXiv: https://arxiv.org/abs/1704.02966 · HTML: https://mlsanity.com/paper/1704.02966/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2017.

## Built on by (most cited first, 21 of 21)

- [EfficientLPS: Efficient LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2102.08009/) (2021)
- [PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions](https://mlsanity.com/paper/2204.12511/) (2022)
- [Equalized Focal Loss for Dense Long-Tailed Object Detection](https://mlsanity.com/paper/2201.02593/) (2022)
- [Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning](https://mlsanity.com/paper/2204.08735/) (2022)
- [Amodal Panoptic Segmentation](https://mlsanity.com/paper/2202.11542/) (2022)
- [Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook](https://mlsanity.com/paper/2312.05391/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Deep learning for precipitation nowcasting: A survey from the perspective of time series forecasting](https://mlsanity.com/paper/2406.04867/) (2024)
- [Semantic Segmentation with Labeling Uncertainty and Class Imbalance](https://mlsanity.com/paper/2102.04566/) (2021)
- [A Comprehensive Survey on Imbalanced Data Learning](https://mlsanity.com/paper/2502.08960/) (2025)
- [Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images](https://mlsanity.com/paper/2302.12491/) (2023)
- [ChessMix: Spatial Context Data Augmentation for Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2108.11535/) (2021)
- [A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design](https://mlsanity.com/paper/2309.03208/) (2023)
- [MoE-SPNet: A Mixture-of-Experts Scene Parsing Network](https://mlsanity.com/paper/1806.07049/) (2018)
- [Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models](https://mlsanity.com/paper/2207.03335/) (2022)
- [Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach](https://mlsanity.com/paper/2601.21243/) (2026)
- [Magnification-independent Histopathological Image Classification with Similarity-based Multi-scale Embeddings](https://mlsanity.com/paper/2107.01063/) (2021)
- [Medical Knowledge-Guided Deep Learning for Imbalanced Medical Image Classification](https://mlsanity.com/paper/2111.10620/) (2021)
- [Learning Appearance and Motion Cues for Panoptic Tracking](https://mlsanity.com/paper/2503.09191/) (2025)
- [Towards High-Quality Image Segmentation: Improving Topology Accuracy by Penalizing Neighbor Pixels](https://mlsanity.com/paper/2603.18671/) (2026)
- [Query by Activity Video in the Wild](https://mlsanity.com/paper/2311.13895/) (2023)

## Abstract (arXiv)

We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic segmentation datasets exhibit long tail distributions with few object categories comprising the majority of data and consequently biasing the classifiers towards them. Our method adaptively re-weights the contributions of each pixel based on their observed losses, targeting under-performing classification results as often encountered for under-represented object classes. Our approach goes beyond conventional cost-sensitive learning attempts through adaptive considerations that allow us to indirectly address both, inter- and intra-class imbalances. We provide a theoretical justification of our approach, complementary to experimental analyses on benchmark datasets. In our experiments on the Cityscapes and Pascal VOC 2012 segmentation datasets we find consistently improved results, demonstrating the efficacy of our approach.